PublicMirrors/you-get
1
0
Fork 0
mirror of https://github.com/soimort/you-get.git synced 2025-02-02 16:24:00 +03:00
Code Issues Actions Packages Projects Releases 1 Wiki Activity

[tumblr] fix extraction

Browse Source
This commit is contained in:
Mort Yao 2021-02-07 14:11:03 +01:00
parent 8b473e7256
commit 92ac149d54
No known key found for this signature in database
GPG Key ID: 07DA00CB78203251
1 changed files with 13 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

19
src/you_get/extractors/tumblr.py
View File

@ -14,7 +14,7 @@ def tumblr_download(url, output_dir='.', merge=True, info_only=False, **kwargs):
return return
import ssl import ssl
ssl_context = request.HTTPSHandler(context=ssl.SSLContext(ssl.PROTOCOL_TLSv1)) ssl_context = request.HTTPSHandler(context=ssl.SSLContext(ssl.PROTOCOL_TLSv1_2)) # server requires TLS v1.2
cookie_handler = request.HTTPCookieProcessor() cookie_handler = request.HTTPCookieProcessor()
opener = request.build_opener(ssl_context, cookie_handler) opener = request.build_opener(ssl_context, cookie_handler)
request.install_opener(opener) request.install_opener(opener)
@ -45,23 +45,30 @@ def tumblr_download(url, output_dir='.', merge=True, info_only=False, **kwargs):
r1(r'<title>([^<\n]*)', html) r1(r'<title>([^<\n]*)', html)
urls = re.findall(r'(https?://[^;"&]+/tumblr_[^;"&]+_\d+\.jpg)', html) +\ urls = re.findall(r'(https?://[^;"&]+/tumblr_[^;"&]+_\d+\.jpg)', html) +\
re.findall(r'(https?://[^;"&]+/tumblr_[^;"&]+_\d+\.png)', html) +\ re.findall(r'(https?://[^;"&]+/tumblr_[^;"&]+_\d+\.png)', html) +\
re.findall(r'(https?://[^;"&]+/tumblr_[^";&]+_\d+\.gif)', html) re.findall(r'(https?://[^;"&]+/tumblr_[^;"&]+_\d+\.gif)', html) +\
re.findall(r'(https?://\d+\.media\.tumblr\.com/[^;"&]+/s\d+x\d+/[^;"&]+\.jpg)', html) +\
re.findall(r'(https?://\d+\.media\.tumblr\.com/[^;"&]+/s\d+x\d+/[^;"&]+\.png)', html) +\
re.findall(r'(https?://\d+\.media\.tumblr\.com/[^;"&]+/s\d+x\d+/[^;"&]+\.gif)', html)
tuggles = {} tuggles = {}
for url in urls: for url in urls:
if url.endswith('.gif'): if url.endswith('.gif'):
hd_url = url hd_url = url
elif url.endswith('.jpg'): elif url.endswith('.jpg'):
hd_url = r1(r'(.+)_\d+\.jpg$', url) + '_1280.jpg' # FIXME: decide actual quality hd_url = url # FIXME: decide actual quality # r1(r'(.+)_\d+\.jpg$', url) + '_1280.jpg'
elif url.endswith('.png'): elif url.endswith('.png'):
hd_url = r1(r'(.+)_\d+\.png$', url) + '_1280.png' # FIXME: decide actual quality hd_url = url # FIXME: decide actual quality # r1(r'(.+)_\d+\.png$', url) + '_1280.png'
else: else:
continue continue
filename = parse.unquote(hd_url.split('/')[-1]) filename = parse.unquote(hd_url.split('/')[-1])
title = '.'.join(filename.split('.')[:-1]) title = '.'.join(filename.split('.')[:-1])
tumblr_id = r1(r'^tumblr_(.+)_\d+$', title) tumblr_id = r1(r'^tumblr_(.+)_\d+$', title) or title
quality = int(r1(r'^tumblr_.+_(\d+)$', title)) try:
quality = int(r1(r'^tumblr_.+_(\d+)$', title))
except:
quality = int(r1(r'/s(\d+)x\d+/', hd_url))
ext = filename.split('.')[-1] ext = filename.split('.')[-1]
try: try:
size = int(get_head(hd_url)['Content-Length']) size = int(get_head(hd_url)['Content-Length'])
if tumblr_id not in tuggles or tuggles[tumblr_id]['quality'] < quality: if tumblr_id not in tuggles or tuggles[tumblr_id]['quality'] < quality: